• 문화기술의 융합
• /
• 제10권4호
• /
• pp.693-700
• /
• 2024

에너지 소비 문제가 전 세계적으로 주요한 이슈로 자리잡아 다양한 부문에서 에너지 소비 및 온실가스 배출 절감에 대한 관심이 크다. 2022년 3월 말 기준 국내 산업단지 총 면적은 606 km2로, 전체 국토면적의 약 0.6 %에 불과한다. 하지만 2018년 기준, 국내 산업단지의 연간 에너지 사용량은 국가 전체 에너지 사용량의 53.5 %, 전체 산업부문 에너지 사용량의 83.1 %를 차지하는 110,866.1천 TOE임으로 확인되었다. 더불어 국가 전체 온실가스 배출량의 45.1 %, 산업부문 온실가스 배출량의 76.8 %를 차지하여 환경에 미치고 있는 영향 또한 상당한 상황임이 확인하였다. 이러한 배경 하에 본 연구에서는 산업단지 차원의 에너지 효율화에 기여하고자, 국내 한 산업단지를 대상으로 에너지 수요 및 공급의 예측을 진행하였으며, 예측 결과값을 포함하여 에너지 모니터링을 위한 시뮬레이터 UI 화면을 설계하였다. 머신러닝 알고리즘 중 다층퍼셉트론 (Multi-Layer Perceptron; MLP)을 사용하였으며, 예측 모델의 최적화 기법으로서 베이지안 최적화 (Bayesian Optimization)를 적용하였다. 본 연구에서 구축한 예측 모델은 산업단지 내 압축공기 수요 유량의 경우는 87.90 %, 공용 공기압축기 공급 가능 유량의 경우는 99.54 %의 예측 정확도를 보였다.

• 한국태양에너지학회 논문집
• /
• 제37권2호
• /
• pp.23-33
• /
• 2017

Accurate prediction of stochastic behavior of occupants is a well known problem for improving prediction performance of building energy use. Many researchers have been tried various sensors that have information on the status of occupant such as $CO_2$ sensor, infrared motion detector, RFID etc. to predict occupants, while others have been developed some algorithm to find occupancy probability with those sensors or some indirect monitoring data such as energy consumption in spaces. In this research, various sensor data and energy consumption data are utilized for decision tree algorithms (C4.5 & CART) for estimation of sub-hourly occupancy status. Although the experiment is limited by space (private room) and period (cooling season), the prediction result shows good agreement of above 95% accuracy when energy consumption data are used instead of measured $CO_2$ value. This result indicates potential of IoT data for awareness of indoor environmental status.

• 대한건축학회논문집:구조계
• /
• 제34권11호
• /
• pp.73-79
• /
• 2018

In this study, for the prediction of energy consumption in the ventilator, one of the components of the air conditioning system, the predicted results were analyzed and accurate by the change in the number of neurons and inputs. The input variables of the prediction model for the energy volume of the fan were the supply air flow rate, the exhaust air flow rate, and the output value was the energy consumption of the fan. A predictive model has been developed to study with the Levenbarg-Marquardt algorithm through 8760 sets of one-minute resolution. Comparison of actual energy use and forecast results showed a margin of error of less than 1% in all cases and utilization time of less than 3% with very high predictability. MBE was distributed with a learning period of 1.7% to 2.95% and a service period of 2.26% to 4.48% respectively, and the distribution rate of ${\pm}10%$ indicated by ASHRAE Guidelines 14 was high.8.

• 한국지열·수열에너지학회논문집
• /
• 제7권1호
• /
• pp.65-71
• /
• 2011

Recently, central and local governments of Korea have established and implemented various energy policies such as making energy map of city level and establishment of environment friendly city plan to materialize low carbon green city. To implement effectively these policies, however, conditions of energy consumption by each administrative district and each usage have to be verified exactly. This study is aimed to suggest a basic data for planing energy policy and energy demand prediction of city level by analyzing energy consumption unit and conditions of city gas by borough and usage in Busan.

• 한국정보처리학회:학술대회논문집
• /
• 한국정보처리학회 2019년도 추계학술발표대회
• /
• pp.585-588
• /
• 2019

Predictions of Energy Consumption for Industries gain an important place in energy management and control system, as there are dynamic and seasonal changes in the demand and supply of energy. This paper presents and discusses the predictive models for energy consumption of the steel industry. Data used includes lagging and leading current reactive power, lagging and leading current power factor, carbon dioxide (tCO2) emission and load type. In the test set, four statistical models are trained and evaluated: (a) Linear regression (LR), (b) Support Vector Machine with radial kernel (SVM RBF), (c) Gradient Boosting Machine (GBM), (d) random forest (RF). Root Mean Squared Error (RMSE), Mean Absolute Error (MAE) and Mean Absolute Percentage Error (MAPE) are used to measure the prediction efficiency of regression designs. When using all the predictors, the best model RF can provide RMSE value 7.33 in the test set.

• 설비공학논문집
• /
• 제12권12호
• /
• pp.1090-1097
• /
• 2000

Predicting building energy use can be useful to evaluate its energy performance. This study proposed empirical approach for predicting building energy use with regression analysis. For the empirical analysis, simple regression models were developed based on the historical energy consumption data as a function of daily outside temperature, the predicting equations were derived for different operational modes and day types, then the equations were applied for predicting energy use in a building. BY selecting a real building as a case study, the feasibilities of the empirical approach for predicting building energy use were examined. The results showed that empirical approach with regression analysis was fairly reliable by demonstrating prediction accuracy of $pm10%$ compared with the actual energy consumption data. It was also verified that the prediction by regression models could be simple and fairly accurate. Thus, it is anticipated that the empirical approach will be useful and reliable tool for many purposes: retrofit savings analysis by estimating energy usage in an existing building or the diagnosis of the building operational problems with real time analysis.

• 전자통신동향분석
• /
• 제39권4호
• /
• pp.32-41
• /
• 2024

Building energy management plays a crucial role in improving energy efficiency and optimizing energy usage. To achieve this, it is important to monitor and analyze energy-related data from buildings in real time using sensors to understand energy consumption patterns and establish optimal operational strategies. Because of the uncertainties in building energy-related data, there are challenges in analyzing these data and formulating operational strategies based on them. Artificial intelligence (AI) technology can help overcome these challenges. This paper investigates past and current research trends in AI technology and examines its future prospects for building energy management. By performing prediction and analysis based on energy consumption or supply data, the future energy demands of buildings can be forecasted and energy consumption can be optimized. Additionally, data related to the surrounding environment, occupancy, and other building energy-related factors can be collected and analyzed using sensors to establish operational strategies aimed at further reducing energy consumption and increasing efficiency. These technologies will contribute to cost savings and help minimize environmental impacts for building owners and operators, ultimately facilitating sustainable building operations.

• 국제학술발표논문집
• /
• The 6th International Conference on Construction Engineering and Project Management
• /
• pp.723-727
• /
• 2015

Building energy use estimation relies on building characteristics, its energy systems, occupants, and weather. Energy estimation of new buildings is considerably an easy task when compared to modeling existing buildings as they require calibration with actual data. Particularly, when energy estimation of existing building stock is warranted at a city-scale, the problem is exacerbated owing to lack of construction drawings and other engineering specifications. However, as collection of buildings and other infrastructure constitute cities, such predictions are a necessary component of developing and maintaining sustainable cities. This paper uses Artificial Neural Network techniques to predict electricity consumption for residential buildings situated in the City of Gainesville, Florida. With the use of 32,813 samples of data vectors that comprise of building floor area, built year, number of stories, and range of monthly energy consumption, this paper extends the prediction to environmental impact assessment of electricity usage at the urban-scale. Among others, one of the applications of the proposed model discussed in this paper is the study of urban scale Life Cycle Assessment, and other decisions related to creating sustainable cities.

• International Journal of Internet, Broadcasting and Communication
• /
• 제7권1호
• /
• pp.23-29
• /
• 2015

Energy constraints of wireless sensor networks are an important challenge. Data Transmission requires energy. Distance between origin and destination has an important role in energy consumption. In addition, the location of base station has a large impact on energy consumption and a specific method not proposed for it. In addition, a obtain model for location of base station proposed. Also a model for distributed clustering is presented by cluster heads. Eventually, a combination of discussed ideas is proposed to improve the energy consumption. The proposed ideas have been implemented over the LEACH-C protocol. Evaluation results show that the proposed methods have a better performance in energy consumption and lifetime of the network in comparison with similar methods.

• 한국빅데이터학회지
• /
• 제6권1호
• /
• pp.127-132
• /
• 2021

우리나라는 자원 빈국인 동시에 에너지 다소비 국가이다. 또한 전기 에너지에 대한 사용량 및 의존도가 매우 높고, 총 에너지 사용의 20% 이상은 건물에서 소비된다. 딥러닝과 머신러닝에 대한 연구가 활발해지면서 다양한 알고리즘을 에너지 효율 분야에 적용하려는 연구가 진행되고 있으며, 에너지의 효율적인 관리를 위한 건물에너지관리시스템(BEMS)의 도입이 늘어가는 추세이다. 본 논문에서는 스마트플러그를 이용하여 직접 수집한 가구당 기기별 에너지 사용량을 바탕으로 데이터베이스를 구축하였다. 또한 RNN과 LSTM 모델을 이용하여 수집한 데이터를 효과적으로 분석 및 예측하는 알고리즘을 구현하였다. 추후 이 데이터는 에너지 사용량 예측을 넘어 전력 소비 패턴 분석 등에 적용할 수 있다. 이는 에너지 효율 개선에 도움이 될 수 있으며, 미래 데이터의 예측을 통해 효과적인 전력 사용량 관리에 도움을 줄 것으로 기대된다.